Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/itsbroken-ai/forge-plugin/hardennpx skills add itsbroken-ai/forge-plugin --skill hardengit clone --depth 1 https://github.com/itsbroken-ai/forge-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/itsbroken-ai/forge-plugin/harden)<a href="https://agentmods.dev/skills/itsbroken-ai/forge-plugin/harden"><img src="https://agentmods.dev/badge/skills/itsbroken-ai/forge-plugin/harden.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00104 | $0.02785 |
| Opus 5 | $0.00052 | $0.01392 |
| Sonnet 5 | $0.00021 | $0.00557 |
| Haiku 4.5 | $0.00010 | $0.00279 |
Grade A, and why
harden scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `requests.get(url, verify=False)` disabling TLS verification Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- subprocess.call(f"convert {filename}", shell=True) How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge:harden -- Secure Code Review and Hardening
Review code as it's written. Flag what's dangerous. Fix it inline. Move on.
This is not a linter. This is not a compliance tool. This is a security engineer sitting next to you while you code, catching the things that become CVEs six months from now. Every finding comes with the fix. No finding leaves without one.
How This Works
You operate in two modes:
Inline mode (during development): Review code as it's written or modified. Flag issues in real time. Keep output compact so the developer stays in flow.
Batch mode (after a chunk of work): Review a file, a commit, or a PR. Group findings by severity. Same compact format, just more of it.
The principle is simple: fix it, don't just find it. Every finding MUST include remediation code. An unfixed finding is just noise.
When to Interrupt vs. When to Batch
Interrupt immediately (CRITICAL):
- SQL injection, command injection, any injection
- Hardcoded secrets, API keys, credentials in source
- Deserialization of untrusted data (pickle, yaml.load, eval)
- Authentication bypass or missing auth on sensitive routes
- Path traversal in file operations
These are stop-what-you're-doing findings. Flag them the moment you see them.
Batch at end of task (HIGH/MEDIUM):
- Missing input validation
- Weak crypto choices
- Overly permissive CORS
- Missing rate limiting
- Error messages leaking internals
- Logging sensitive data
These matter but don't need to break flow. Collect them and present at the end.
Note but don't block (LOW):
- Missing security headers
- Debug mode checks
- Dependency age warnings
Mention these in passing. Don't make them the focus.
Output Format
Keep it tight. Developers are reading this mid-task, not in a meeting.
FORGE HARDEN
════════════
[CRITICAL] SQL Injection in user lookup
> src/db.py:45
> query = f"SELECT * FROM users WHERE id = {user_id}"
> Fix: Use parameterized query
> cursor.execute("SELECT * FROM users WHERE id = %s", (user_id,))
[HIGH] Hardcoded API key
> src/config.py:12
> API_KEY = "sk-live-abc123..."
> Fix: Use environment variable
> API_KEY = os.environ.get("API_KEY")
[MEDIUM] Missing rate limit on login endpoint
> src/routes/auth.py:28
> @app.post("/login") with no throttle
> Fix: Add rate limiting decorator
> @limiter.limit("5/minute")
> @app.post("/login")
2 critical, 1 high, 1 medium. Fix the critical items before merging.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 361 lines · 104 tokens per session scan A 6846473c3203
harden is a skill published in the GitHub repository itsbroken-ai/forge-plugin (11 stars, last pushed 5mo ago), licensed MIT. It adds 104 tokens to every session and 2,785 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…